speechbrainteam commited on
Commit
67585f1
1 Parent(s): d31e48e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -33,7 +33,7 @@ For a better experience, we encourage you to learn more about
33
 
34
  ## Pipeline description
35
 
36
- This ASR system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings.
37
 
38
  ## Install SpeechBrain
39
 
 
33
 
34
  ## Pipeline description
35
 
36
+ This system is composed of an ECAPA-TDNN model. It is a combination of convolutional and residual blocks. The embeddings are extracted using attentive statistical pooling. The system is trained with Additive Margin Softmax Loss. Speaker Verification is performed using cosine distance between speaker embeddings.
37
 
38
  ## Install SpeechBrain
39